In [1]:

    

import pandas as pd


    

In [2]:

    

checkin = pd.read_csv('../../../data/interim/US_cities_only/checkin_US.csv')


    

In [3]:

    

checkin.head()


    

    
Out[3]:






  

    

      

      
business_id
      
time
      
type
    
  
  

    

      
0
      
7KPBkxAOEtb3QeIL9PEErg
      
[Fri-0:2, Sat-0:1, Sun-0:1, Wed-0:2, Sat-1:2, ...
      
checkin
    
    

      
1
      
kREVIrSBbtqBhIYkTccQUg
      
[Mon-13:1, Thu-13:1, Sat-16:1, Wed-17:1, Sun-1...
      
checkin
    
    

      
2
      
nhZ1HGWD8lMErdn3FuWuTQ
      
[Fri-0:1, Sat-0:1, Sun-0:1, Thu-0:1, Wed-0:1, ...
      
checkin
    
    

      
3
      
8bY6M2yiWOF2ilfmGS34Fw
      
[Sat-11:1, Fri-13:1, Thu-14:1]
      
checkin
    
    

      
4
      
zNVot5_XHsxwfKdiFjk_aA
      
[Mon-0:1, Fri-1:1, Sun-1:1, Tue-1:1, Wed-11:1,...
      
checkin
    
  

In [4]:

    

# Cleaning 'time' column

checkin['time'] = checkin['time'].map(lambda x: x[1:-1].split(','))


    

In [5]:

    

# Writing clean 'checkin' dataframe to csv

checkin.to_csv('../../../data/interim/clean_US_cities/checkin_clean.csv', encoding='utf-8', index=False)